The paper shows that the signal‑to‑noise ratio (SNR) distribution is key to achieving fine‑grained spatial control in flow‑matching generative models. By training on high‑noise regimes rather than a centered SNR distribution, the authors raise layout adherence from 25.9 % to 80.8 % on a synthetic benchmark, approaching the 83.6 % ceiling of the underlying variational autoencoder. These insights also improve real‑world layout accuracy on COCO, boosting average precision from 1.0 % to 57.3 % without changing the model architecture.
By Martin Thi{\ss}en, Elke Hergenr\"other
arXiv:2608.01896v2 Announce Type: replace
Abstract: Existing generative models for earth observation (EO) predominantly rely on fine-tuning natural image priors, which limits their scalability and in...
By Jeonghyeok Do, Munchurl Kim
arXiv:2505. 04486v4 Announce Type: replace-cross Abstract: Flow matching models have shown great potential in image generation tasks among probabilistic generative models.
By Anirban Samaddar, Yixuan Sun, Viktor Nilsson, Sandeep Madireddy
arXiv:2607. 29180v1 Announce Type: cross Abstract: Text-to-motion generation must produce motions that are semantically correct, temporally coherent, and physically plausible.
By Yifei Zhu, Mingyi Shi, Yangyang Cai, Miao Cheng, Yoshifumi Kitamura, Taku Komura
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.
Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions.
The paper investigates how visual representations contribute to pixel diffusion transformers and finds that higher representation quality does not always improve generative performance, and that separating architecture into specialized decoders mainly redistributes modeling rather than enhancing generative suitability. Based on these findings, the authors propose Representation Guidance (RG), a method that compacts generation-relevant information into a low-dimensional bottleneck and explicitly uses it to steer decoder generation. RG achieves state‑of‑the‑art results on ImageNet 256×256 with fewer parameters, scales efficiently, and extends to text‑to‑image tasks with strong benchmark performance.
By Zihao Pan, Mengting Chen, Cheng Shi, Taihang Hu, Zhengrong Yue, Zikang Wang, Yuan Wang, Wei Li, Sibei Yang
The paper introduces Composite Subspace Flow Matching (CSFM), a representation learning method that minimizes variance by inverting a deterministic degradation curriculum across spectral, color, and illumination subspaces. CSFM uses hard temporal style truncation to constrain an encoder, encouraging it to ignore transient style artifacts while preserving persistent content. Experiments on CIFAR-10, CIFAR-100, and STL-10 demonstrate that CSFM achieves competitive discriminative transferability and generative synthesis, outperforming standard optimal transport flows in linear probing and few‑shot classification while maintaining a smooth latent space.
By Jos\'e Afonso, M\'ario Figueiredo
arXiv:2609.35734v2 Announce Type: replace
Abstract: Novel view synthesis from sparse images must reconcile faithful reconstruction of observed regions with plausible completion of unseen content, whi...
By Kerui Ren, Tao Lu, Linning Xu, Changjian Jiang, Mu Huang, Chunhua Shen, Mulin Yu, Bo Dai
arXiv:2609.35763v3 Announce Type: replace
Abstract: Distributional training provides collective supervision for one-step visual generation by matching real and generated features in frozen representa...
By Chi Zhang, Shi Haoyang, Yueyi Liu, Ruichuan An, Junkang Zhou, Chang Li, Xiuyuan Lu, Yichi Zhang, Bo Wang, Yuhang Wu, Sen Cui, Miao Liu
Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly.
arXiv:2605.12957v2 Announce Type: replace
Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
By Hanxin Zhu, Cong Wang, Peiyan Tu, Jiayi Luo, Tianyu He, Xin Jin, Zhibo Chen